{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015645779550966126,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015645779550966127,
      "grad_norm": 0.23797346651554108,
      "learning_rate": 2e-05,
      "loss": 0.904,
      "step": 1
    },
    {
      "epoch": 0.00015645779550966127,
      "eval_loss": 0.7949446439743042,
      "eval_runtime": 152.3802,
      "eval_samples_per_second": 17.666,
      "eval_steps_per_second": 8.833,
      "step": 1
    },
    {
      "epoch": 0.00031291559101932255,
      "grad_norm": 0.19366322457790375,
      "learning_rate": 4e-05,
      "loss": 0.7911,
      "step": 2
    },
    {
      "epoch": 0.0004693733865289838,
      "grad_norm": 0.20207928121089935,
      "learning_rate": 6e-05,
      "loss": 0.7439,
      "step": 3
    },
    {
      "epoch": 0.0004693733865289838,
      "eval_loss": 0.7944307923316956,
      "eval_runtime": 152.5415,
      "eval_samples_per_second": 17.648,
      "eval_steps_per_second": 8.824,
      "step": 3
    },
    {
      "epoch": 0.0006258311820386451,
      "grad_norm": 0.18810410797595978,
      "learning_rate": 8e-05,
      "loss": 0.713,
      "step": 4
    },
    {
      "epoch": 0.0007822889775483063,
      "grad_norm": 0.2186315655708313,
      "learning_rate": 0.0001,
      "loss": 0.7644,
      "step": 5
    },
    {
      "epoch": 0.0009387467730579676,
      "grad_norm": 0.22385373711585999,
      "learning_rate": 0.00012,
      "loss": 0.7234,
      "step": 6
    },
    {
      "epoch": 0.0009387467730579676,
      "eval_loss": 0.7881787419319153,
      "eval_runtime": 252.5338,
      "eval_samples_per_second": 10.66,
      "eval_steps_per_second": 5.33,
      "step": 6
    },
    {
      "epoch": 0.001095204568567629,
      "grad_norm": 0.20991194248199463,
      "learning_rate": 0.00014,
      "loss": 0.6983,
      "step": 7
    },
    {
      "epoch": 0.0012516623640772902,
      "grad_norm": 0.24949102103710175,
      "learning_rate": 0.00016,
      "loss": 0.7136,
      "step": 8
    },
    {
      "epoch": 0.0014081201595869514,
      "grad_norm": 0.24496372044086456,
      "learning_rate": 0.00018,
      "loss": 0.7158,
      "step": 9
    },
    {
      "epoch": 0.0014081201595869514,
      "eval_loss": 0.7681970000267029,
      "eval_runtime": 318.6529,
      "eval_samples_per_second": 8.448,
      "eval_steps_per_second": 4.224,
      "step": 9
    },
    {
      "epoch": 0.0015645779550966126,
      "grad_norm": 0.2570650279521942,
      "learning_rate": 0.0002,
      "loss": 0.8679,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1619596113346560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}